© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5995
    Prev
    Next
    INDEX
    Explanations

    terms related to comfort and suitability in products or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.11
    ↵
    -0.97
     […]
    -0.94
    <eos>
    -0.84
      
    -0.83
     
    -0.83
    .”
    -0.82
    ...
    -0.81
    …
    -0.79
     [...]
    -0.74
    POSITIVE LOGITS
    rungsseite
    0.79
     Савезне
    0.77
     الحره
    0.74
    Datuak
    0.72
     дописавши
    0.71
     ModelExpression
    0.70
     мәкалә
    0.67
    enderror
    0.67
     виправивши
    0.67
     تضيفلها
    0.67
    Activations Density 0.002%

    No Known Activations